Prompt, Context, Loop: The Three Engineering Layers Every RAG System Is Built On
Enterprise Document Intelligence [Vol.1 #M2] – Every RAG system is built in three engineering layers stacked on one LLM call:…
Category: General
Found Friday S5I5: The week agents needed guardrails.
Found Friday · Season 5 · Issue 5 The week agents needed guardrails. This issue starts with the OpenAI and…
How to Build CLI Agents with Python & Ollama
Create a local CLI Agent from scratch completely for free The post How to Build CLI Agents with Python &…
The AI Was the Easy Part: What Is a Forward-Deployed Engineer in a Supply Chain?
What actually makes a Forward Deployed Engineer, told through one supply chain project. The post The AI Was the Easy…
How to Apply Coding Agents to Non-Programming Tasks
Perform non-programming tasks with coding agents The post How to Apply Coding Agents to Non-Programming Tasks appeared first on Towards…
I Replaced a 15-Minute Booking Process with a LangGraph AI Agent
A step-by-step guide to building, running, and monitoring a stateful customer support agent using Python, LangGraph, and Langfuse. The post…
Coding Agents Don’t Need Bigger Context Windows — They Need a Context Compiler
Most coding agents treat prompt construction like retrieval: gather more files, add more context, hope the model figures it out.…
Put the Agent Inside the Workflow
A hybrid LLM application pattern that combines a predefined workflow with adaptive agent behavior The post Put the Agent Inside…
The 3× Token Bill We Didn’t See Coming
How a seemingly harmless move to a multi-agent architecture quietly tripled our LLM costs and what actually fixed it. The…
When the Code Becomes the CEO: Why Your Next Manager Might Be a Decentralized Agentic Loop
In five to ten years, the sharpest manager in your company might not be human, might not sleep, and might…
How to Debug AI Coding Agents When They Change the Wrong Thing
A practical tutorial for recording model tool requests, real function results, patches, checks, screenshots, and a saved run log. The…
How Benders Decomposition Works Part I: Optimality Cuts
A friendly introduction to one of the most powerfull optimization techniques using the uncapacitated facility location problem The post How…
Daniela Rus receives Bavarian Minister-President’s High-Tech Prize
Daniela Rus, director of MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Panasonic Professor of Computer Science, has…
The Python Ecosystem That Changed AI Development
How one open-source ecosystem made state-of-the-art AI accessible The post The Python Ecosystem That Changed AI Development appeared first on…
How to Organize All of Your Coding Agent Tasks
Optimise how you interact with your coding agents The post How to Organize All of Your Coding Agent Tasks appeared…
Gemini Robotics ER 2: powering robotics with video understanding, task orchestration, and multi-robot collaboration
Gemini Robotics ER 2 helps robots reason, collaborate, and solve real-world tasks. It represents a step change in video understanding,…
How to Decode the Temperature Parameter in LLMs
How statistical physics explains the transition from deterministic predictions to generative AI. The post How to Decode the Temperature Parameter…
Prompt Engineering Is Solved—Prompt Management Isn’t
Prompt engineering helps you write better prompts—but it doesn’t help you change them safely. This article explores a common production…
Why Your Best Predictive Model Gives the Wrong Treatment Effect
Why prediction-driven variable selection misses confounders and how Bayesian Adjustment for Confounding attempts to fix it. The post Why Your…
How a medical database developed at MIT evolved into a global standard of data-sharing
Before the advancement of scientific data storage and collaboration via the cloud, medical investigators seeking health research breakthroughs had to…
Los Movimientos, Part II: Solving Large Pickup-and-Delivery Problems with Adaptive Large Neighborhood Search
Building an ALNS heuristic in Python for vehicle routing, time windows, capacity constraints, and mandatory driver breaks. The post Los…
How Much Does a Local LLM Actually Cost to Run? I Measured Every Watt on Apple Silicon
Five models, sustained generation, real wall-socket energy at $0.31/kWh — and the surprise the RTX-3090 numbers predicted, only bigger. The…
Don’t Just “Throw Adam at It”: Misunderstanding Adam Will Cost You
You “vibe coded” the import. Understand Adam’s optimization dynamics, why it fails spectacularly, and how to fix it. The post…
Backpropagation Explained for Beginners (Part 2): There Has to Be a Better Way
The idea that makes backpropagation possible. The post Backpropagation Explained for Beginners (Part 2): There Has to Be a Better…
“Los Movimientos”: The Routing Problem That Nearly Broke My Spirit
Using mathematical optimization to solve a pickup-and-delivery problem with time windows. The post “Los Movimientos”: The Routing Problem That Nearly…
Reducing Human Annotation with ML Active Learning
In a world where human time is expensive, learn how to use it only when really necessary The post Reducing…
The Most Beautiful Statistic: The History and the Science of the Humble Mean
The mean keeps making its usefulness felt in all sorts of situations, often in truly non-obvious ways The post The…
How I Reproduced BM25, Dense Retrieval, and SPLADE on a 16GB MacBook
A practical reproduction of three retrieval baselines, including the crashes, fixes, and score checks that matter for RAG systems. The…
How to Efficiently Prompt Claude Code
Maximize your efficiency with Claude Code The post How to Efficiently Prompt Claude Code appeared first on Towards Data Science.
How to Give an LLM Agent a Browser
Building a browser-use agent with OpenAI Agents SDK and Playwright MCP The post How to Give an LLM Agent a…
How to Optimize Vector Search When RAM Gets Too Expensive: On-Disk vs. In-Memory ANN Indexes
Architecting cost-effective infrastructure by navigating the latency and storage trade-offs of HNSW, SPANN, and DiskANN The post How to Optimize…
The Fluid Simulator That Doesn’t Solve the Fluid Equations
I generated a Kármán vortex street without solving a single fluid equation. Here’s how the Lattice Boltzmann Method gets there…
Tabular LLMs: An Introduction to the Foundation Models That Predict Your Spreadsheet
Tabular foundation models predict the missing column of any spreadsheet zero-shot, the way an LLM completes text — and on…
Loop Engineering for RAG Generation: An LLM Cascade from a Cheap Local Model Up to a Hosted Flagship
Enterprise Document Intelligence [Vol.1 #8quater] – Two angles on the cascade, cost and a validation loop, backed by a real…
Working to automate nuclear plant operations
For nuclear to be considered as a viable clean energy source, it has to be competitively priced and economical to…
When Data Science Makes Us Sad: The Story of an Overbooked Flight
$8 million vs $5k + Potentially Going Viral The post When Data Science Makes Us Sad: The Story of an…
Most RAG Hallucinations Are Extraction Errors: Seven Patterns for a Typed Generation Contract
Enterprise Document Intelligence [Vol.1 #8ter] – Naming the RAG error correctly matters: model reads the context, so a wrong answer…
Lessons Learned After 8.5 Years of ML
Patience, Optimism, Discipline, Projects, Teams The post Lessons Learned After 8.5 Years of ML appeared first on Towards Data Science.
Why Adding More AI Agents Made Our System Slower
The hidden cost of asynchronous systems, how tiny CPU tasks quietly became our biggest bottleneck while scaling hundreds of LLM…
MIT projects selected for funding under US Department of Energy’s Genesis Mission
MIT researchers are set to contribute to the U.S. Department of Energy’s (DOE) Genesis Mission, with 15 collaborative projects among those…
Professor Emeritus Dimitri Bertsekas, influential computer scientist and prolific author, dies at 83
Dimitri Bertsekas PhD ’71, the Jerry McAfee (1940) Emeritus Professor in Engineering in the Department of Electrical Engineering and Computer…
Loop Engineering for RAG Generation: iterate top-k one at a time
Enterprise Document Intelligence [Vol.1 #8bis] – Two regimes for sending retrieved candidates to the generation brick, the sufficiency signal that…
Build an LLM Agent That Can Write and Run Code
A hands-on walkthrough of code execution with the OpenAI Agents SDK and Docker The post Build an LLM Agent That…
Accelerating the frontiers of scientific discovery: Google’s $40M commitment to the Genesis Mission
Google commits $40M in AI tokens and credits for the Genesis Mission
Detecting Vulnerabilities in Agent Skills with SkillSpector: From Green Checkmark to Real Security Judgment
Static analysis nailed the malicious skill and over-flagged the useful one. The gap between those results is where human judgement…
Prompt Engineering Isn’t Enough: How Four Bricks of Context Engineering Stop RAG Hallucinations
Enterprise Document Intelligence [Vol.1 #9bis] – Your RAG isn’t hallucinating, it’s answering the wrong context faithfully. On real NIST and…
I Tried Fine-Tuning a Robot AI Model on Colab. Here Is What Worked
A reproducible 100-step LoRA fine-tuning run for OpenVLA, with dataset checks, Colab setup, training metrics, and W&B evidence. The post…
Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber
We’re introducing new Gemini models, including Gemini 3.6 Flash, 3.5 Flash-Lite and 3.5 Flash Cyber.
How Much of a Data Science Workflow Can Run on a GPU Today? Part 1: Accelerating Data Preparation
Exploring GPU acceleration with cuDF, cudf.pandas, and the Polars GPU Engine The post How Much of a Data Science Workflow Can…